English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Transfer learning research attempts to make model induction transferableacross different domains. This method assumes that specific informationregarding to which domain each instance belongs is known. This paper helps toextend the capability of transfer learning for linear regression problems tosituations where the domain information is uncertain or unknown; in fact, theframework can be extended to classification problems. For normal datasets, weassume that some latent domain information is available for transfer learning.The instances in each domain can be inferred by different parameters. We obtainthis domain information from the distribution of the regression coefficientscorresponding to the explanatory variable $x$ as well as the response variable$y$ based on a Dirichlet process, which is more reasonable. As a result, wetransfer not only variable $x$ as usual but also variable $y$, which ischallenging since the testing data have no response value. Previous work mainlyovercomes the problem via pseudo-labelling based on transductive learning,which introduces serious bias. We provide a novel framework for analysing theproblem and considering this general situation: the joint distribution ofvariable $x$ and variable $y$. Furthermore, our method controls the bias wellcompared with previous work. We perform linear regression on the new featurespace that consists of different latent domains and the target domain, which isfrom the testing data. The experimental results show that the proposed modelperforms well on real datasets.

Automatic Cross-Domain Transfer Learning for Linear Regression